© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3753
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically those related to a certain region

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Yukon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.89
    æĸ¹
    -0.84
    Ĥª
    -0.80
     actionGroup
    -0.75
    ħĭ
    -0.74
    senal
    -0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    ::::::::
    -0.69
    RESULTS
    -0.67
     [|
    -0.67
    POSITIVE LOGITS
    on
    1.10
    etheless
    1.05
    emon
    0.99
    auts
    0.99
    ons
    0.95
    aut
    0.91
    essee
    0.91
    ucle
    0.90
    nen
    0.90
    acci
    0.85
    Activations Density 0.025%

    No Known Activations